Instructions to use mlx-community/Lens-Turbo-3.8B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Lens-Turbo-3.8B-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Lens-Turbo-3.8B-4bit mlx-community/Lens-Turbo-3.8B-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Point code-repo links to canonical xocialize/lens-mlx
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ reference (DiT cosine 0.999999); this variant inherits that port.
|
|
| 19 |
## Usage
|
| 20 |
|
| 21 |
```python
|
| 22 |
-
from lens_mlx.pipeline_mlx import LensPipeline # github.com/xocialize
|
| 23 |
|
| 24 |
# `base` = a microsoft/Lens snapshot (tokenizer + GPT-OSS encoder + FLUX.2 VAE).
|
| 25 |
pipe = LensPipeline.from_pretrained(base, dit_repo="mlx-community/Lens-Turbo-3.8B-4bit")
|
|
|
|
| 19 |
## Usage
|
| 20 |
|
| 21 |
```python
|
| 22 |
+
from lens_mlx.pipeline_mlx import LensPipeline # github.com/xocialize/lens-mlx
|
| 23 |
|
| 24 |
# `base` = a microsoft/Lens snapshot (tokenizer + GPT-OSS encoder + FLUX.2 VAE).
|
| 25 |
pipe = LensPipeline.from_pretrained(base, dit_repo="mlx-community/Lens-Turbo-3.8B-4bit")
|